© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9676
    Prev
    Next
    INDEX
    Explanations

    student learning over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    0.57
    ↵
    0.52
    8
    0.52
    大
    0.52
    د
    0.50
    Have
    0.50
    9
    0.49
    Ｌ
    0.49
    이
    0.49
    आई
    0.48
    POSITIVE LOGITS
    unehm
    0.53
    学的
    0.50
    𒌍
    0.49
    ⵅ
    0.49
    র্যের
    0.49
    ⴽ
    0.49
    gewicht
    0.47
     আস্থা
    0.47
     hemicontinuous
    0.47
    getStudentNo
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.